samsung SM-S908B
Geekbench ML Score
851
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | Kosst_Amojan |
| Upload Date | April 03 2022 01:38 PM |
| Views | 5 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | samsung SM-S908B |
| Model ID | samsung SM-S908B |
| Motherboard | s5e9925 |
| Governor | energy_aware |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.82 GHz |
| Cluster 1 | 4 Cores @ 1.82 GHz |
| Cluster 2 | 3 Cores @ 2.52 GHz |
| Cluster 3 | 1 Core @ 2.80 GHz |
| Memory Information | |
|---|---|
| Size | 10.27 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
250
26.8 IPS |
|
|
Image Classification (F16)
|
100% |
633
67.9 IPS |
|
|
Image Classification (I8)
|
80% |
585
62.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
1202
7.42 IPS |
|
|
Image Segmentation (F16)
|
100% |
3125
19.3 IPS |
|
|
Image Segmentation (I8)
|
89% |
2998
18.5 IPS |
|
|
Pose Estimation (F32)
|
100% |
454
1.84 IPS |
|
|
Pose Estimation (F16)
|
100% |
1097
4.44 IPS |
|
|
Pose Estimation (I8)
|
80% |
1077
4.36 IPS |
|
|
Object Detection (F32)
|
100% |
247
8.65 IPS |
|
|
Object Detection (F16)
|
100% |
585
20.5 IPS |
|
|
Object Detection (I8)
|
54% |
566
19.9 IPS |
|
|
Face Detection (F32)
|
100% |
1138
13.1 IPS |
|
|
Face Detection (F16)
|
97% |
2285
26.3 IPS |
|
|
Face Detection (I8)
|
76% |
2235
25.7 IPS |
|
|
Text Classification (F32)
|
100% |
309
122.3 IPS |
|
|
Text Classification (F16)
|
98% |
582
230.1 IPS |
|
|
Machine Translation (F32)
|
100% |
995
153.4 IPS |
|
|
Machine Translation (F16)
|
100% |
991
152.8 IPS |
